Machine Learning Improves Risk Stratification in Myelodysplastic Neoplasms: An Analysis of the Spanish Group of Myelodysplastic Syndromes
Ontology highlight
ABSTRACT:
SUBMITTER: Mosquera Orgueira A
PROVIDER: S-EPMC10569758 | biostudies-literature | 2023 Oct
REPOSITORIES: biostudies-literature
Similar Datasets
Project description:The International Staging System (ISS) and the Revised International Staging System (R-ISS) are commonly used prognostic scores in multiple myeloma (MM). These methods have significant gaps, particularly among intermediate-risk groups. The aim of this study was to improve risk stratification in newly diagnosed MM patients using data from three different trials developed by the Spanish Myeloma Group. For this, we applied an unsupervised machine learning clusterization technique on a set of clinical, biochemical and cytogenetic variables, and we identified two novel clusters of patients with significantly different survival. The prognostic precision of this clusterization was superior to those of ISS and R-ISS scores, and appeared to be particularly useful to improve risk stratification among R-ISS 2 patients. Additionally, patients assigned to the low-risk cluster in the GEM05 over 65 years trial had a significant survival benefit when treated with VMP as compared with VTD. In conclusion, we describe a simple prognostic model for newly diagnosed MM whose predictions are independent of the ISS and R-ISS scores. Notably, the model is particularly useful in order to re-classify R-ISS score 2 patients in 2 different prognostic subgroups. The combination of ISS, R-ISS and unsupervised machine learning clusterization brings a promising approximation to improve MM risk stratification.
| S-EPMC9038663 | biostudies-literature
Project description:The accurate assessment of a patient's risk of adverse events remains a mainstay of clinical care. Commonly used risk metrics have been based on logistic regression models that incorporate aspects of the medical history, presenting signs and symptoms, and lab values. More sophisticated methods, such as Artificial Neural Networks (ANN), form an attractive platform to build risk metrics because they can easily incorporate disparate pieces of data, yielding classifiers with improved performance. Using two cohorts consisting of patients admitted with a non-ST-segment elevation acute coronary syndrome, we constructed an ANN that identifies patients at high risk of cardiovascular death (CVD). The ANN was trained and tested using patient subsets derived from a cohort containing 4395 patients (Area Under the Curve (AUC) 0.743) and validated on an independent holdout set containing 861 patients (AUC 0.767). The ANN 1-year Hazard Ratio for CVD was 3.72 (95% confidence interval 1.04-14.3) after adjusting for the TIMI Risk Score, left ventricular ejection fraction, and B-type natriuretic peptide. A unique feature of our approach is that it captures small changes in the ST segment over time that cannot be detected by visual inspection. These findings highlight the important role that ANNs can play in risk stratification.
| S-EPMC5627253 | biostudies-literature
Project description:BackgroundCoronary heart disease (CHD) and cerebral ischemic stroke (CIS) are two major types of cardiovascular disease (CVD) that are increasingly exerting pressure on the healthcare system worldwide. Machine learning holds great promise for improving the accuracy of disease prediction and risk stratification in CVD. However, there is currently no clinically applicable risk stratification model for the Asian population. This study developed a machine learning-based CHD and CIS model to address this issue.MethodsA case-control study was conducted based on 8,624 electronic medical records from 2008 to 2019 at the Tongji Hospital in Wuhan, China. Two machine learning methods (the random down-sampling method and the random forest method) were integrated into 2 ensemble models (the CHD model and the CIS model). The trained models were then interpreted using Shapley Additive exPlanations (SHAP).ResultsThe CHD and CIS models achieved good performance with the areas under the receiver operating characteristic curve (AUC) of 0.895 and 0.884 in random testing, and 0.905 and 0.889 in sequential testing, respectively. We identified 4 common factors between CHD and CIS: age, brachial-ankle pulse wave velocity, hypertension, and low-density lipoprotein cholesterol (LDL-C). Moreover, carcinoembryonic antigen (CEA) was identified as an independent indicator for CHD.ConclusionsOur ensemble models can provide risk stratification for CHD and CIS with clinically applicable performance. By interpreting the trained models, we provided insights into the common and unique indicators in CHD and CIS. These findings may contribute to a better understanding and management of risk factors associated with CVD.
| S-EPMC9708484 | biostudies-literature
Project description:In a previous study, we identified somatic mutations of SF3B1, a gene encoding a core component of RNA splicing machinery, in patients with myelodysplastic syndrome (MDS). Here, we define the clinical significance of these mutations in MDS and myelodysplastic/myeloproliferative neoplasms (MDS/MPN). The coding exons of SF3B1 were screened using massively parallel pyrosequencing in patients with MDS, MDS/MPN, or acute myeloid leukemia (AML) evolving from MDS. Somatic mutations of SF3B1 were found in 150 of 533 (28.1%) patients with MDS, 16 of 83 (19.3%) with MDS/MPN, and 2 of 38 (5.3%) with AML. There was a significant association of SF3B1 mutations with the presence of ring sideroblasts (P < .001) and of mutant allele burden with their proportion (P = .002). The mutant gene had a positive predictive value for ring sideroblasts of 97.7% (95% confidence interval, 93.5%-99.5%). In multivariate analysis including established risk factors, SF3B1 mutations were found to be independently associated with better overall survival (hazard ratio = 0.15, P = .025) and lower risk of evolution into AML (hazard ratio = 0.33, P = .049). The close association between SF3B1 mutations and disease phenotype with ring sideroblasts across MDS and MDS/MPN is consistent with a causal relationship. Furthermore, SF3B1 mutations are independent predictors of favorable clinical outcome, and their incorporation into stratification systems might improve risk assessment in MDS.
| S-EPMC3236114 | biostudies-literature
Project description:Hypomethylating agents (HMA) prolong survival and improve cytopenias in individuals with higher-risk myelodysplastic syndrome (MDS). Only 30-40% of patients, however, respond to HMAs, and responses may not occur for more than 6 months after HMA initiation. We developed a model to more rapidly assess HMA response by analyzing early changes in patients' blood counts. Three institutions' data were used to develop a model that assessed patients' response to therapy 90 days after the initiation using serial blood counts. The model was developed with a training cohort of 424 patients from 2 institutions and validated on an independent cohort of 90 patients. The final model achieved an area under the receiver operating characteristic curve (AUROC) of 0.79 in the train/test group and 0.84 in the validation group. The model provides cohort-wide and individual-level explanations for model predictions, and model certainty can be interrogated to gauge the reliability of a given prediction.
| S-EPMC9490588 | biostudies-literature
Project description:Dysplasia and proliferation are histological properties that can be used to diagnose and categorize myeloid tumors in myelodysplastic syndromes (MDS) and myeloproliferative neoplasms (MPN). However, these conditions are not exclusive, and overlap between them leads to another classification, MDS/MPN. As well as phenotype continuity, these three conditions may have genetic relationships that have not yet been identified. This study aimed to obtain their mutational profiles by meta-analysis and explore possible similarities and differences. We reviewed screening studies of gene mutations, published from January 2000 to March 2020, from PubMed and Web of Science. Fifty-three articles were eligible for the meta-analysis, and at most 9,809 cases were involved for any gene. The top mutant genes and their pooled mutation rates were as follows: SF3B1 (20.2% [95% CI 11.6-30.5%]) in MDS, TET2 (39.2% [95% CI 21.7-52.0%]) in MDS/MPN, and JAK2 (67.9% [95% CI 64.1-71.6%]) in MPN. Subgroup analysis revealed that leukemic transformation-related genes were more commonly mutated in high-risk MDS (MDS with multilineage dysplasia and MDS with excess blasts) than that in other MDS entities. Thirteen genes including ASXL1, U2AF1, SRSF2, SF3B1, and ZRSR2 had significantly higher mutation frequencies in primary myelofibrosis (PMF) compared with essential thrombocythemia and polycythemia vera; this difference distinguished PMF from MPN and likened it to MDS. Chronic myelomonocytic leukemia and atypical chronic myeloid leukemia were similar entities but showed several mutational differences. A heat map demonstrated that juvenile myelomonocytic leukemia and MDS/MPN with ring sideroblasts and thrombocytosis were two distinct entities, whereas MDS/MPN-unclassifiable was closest to high-risk MDS. Such genetic closeness or difference reflected features in the pathogenesis, diagnosis, treatment, and progression of these conditions, and could inspire future genetic studies.
| S-EPMC7575718 | biostudies-literature
Project description:Morphologic interpretation is the standard in diagnosing myelodysplastic syndrome (MDS), but it has limitations, such as varying reliability in pathologic evaluation and lack of integration with genetic data. Somatic events shape morphologic features, but the complexity of morphologic and genetic changes makes clear associations challenging. This article interrogates novel clinical subtypes of MDS using a machine-learning technique devised to identify patterns of cooccurrence among morphologic features and genomic events. We sequenced 1079 MDS patients and analyzed bone marrow morphologic alterations and other clinical features. A total of 1929 somatic mutations were identified. Five distinct morphologic profiles with unique clinical characteristics were defined. Seventy-seven percent of higher-risk patients clustered in profile 1. All lower-risk (LR) patients clustered into the remaining 4 profiles: profile 2 was characterized by pancytopenia, profile 3 by monocytosis, profile 4 by elevated megakaryocytes, and profile 5 by erythroid dysplasia. These profiles could also separate patients with different prognoses. LR MDS patients were classified into 8 genetic signatures (eg, signature A had TET2 mutations, signature B had both TET2 and SRSF2 mutations, and signature G had SF3B1 mutations), demonstrating association with specific morphologic profiles. Six morphologic profiles/genetic signature associations were confirmed in a separate analysis of an independent cohort. Our study demonstrates that nonrandom or even pathognomonic relationships between morphology and genotype to define clinical features can be identified. This is the first comprehensive implementation of machine-learning algorithms to elucidate potential intrinsic interdependencies among genetic lesions, morphologies, and clinical prognostic in attributes of MDS.
| S-EPMC7702479 | biostudies-literature
Project description:Although most cases of myeloid neoplasms are sporadic, a small subset has been associated with germline mutations. The 2016 revision of the World Health Organization classification included these cases in a myeloid neoplasm group with a predisposing germline mutational background. These patients must have a different management and their families should get genetic counseling. Cases identification and outline of the major known syndromes characteristics will be discussed in this text.
| S-EPMC5600909 | biostudies-literature
Project description:Papillary thyroid cancer (PTC) is the most common type of thyroid carcinoma accounting for 85%. Most PTCs have a low risk of recurrence and metastasizing and not all low-risk PTCs need immediate surgery. However, cases are often recognized as low-risk only after surgery. Our study aimed to find a preoperative stratification strategy to distinguish low- from intermediate- and higher-risk cases to avoid unnecessary thyroidectomies or delayed surgeries. We conducted a retrospective, multicenter study with 558 PTCs comprising 118 pre- (n=118) and post- (n=440) operative samples. PTC samples were classified into high-, intermediate-, or low-risk according to the traditional postoperative assessment. From each patient, we collected clinical information, immunological indices, and BRAFV600E mutation assessment. Proteomic profiling was conducted through data-independent acquisition mode by mass spectrometry.
2024-03-13 | PXD050577 |
Project description:Patients with high-grade serous ovarian cancer suffer poor prognosis and variable response to treatment. Known prognostic factors for this disease include homologous recombination deficiency status, age, pathological stage and residual disease status after debulking surgery. Recent work has highlighted important prognostic information captured in computed tomography and histopathological specimens, which can be exploited through machine learning. However, little is known about the capacity of combining features from these disparate sources to improve prediction of treatment response. Here, we assembled a multimodal dataset of 444 patients with primarily late-stage high-grade serous ovarian cancer and discovered quantitative features, such as tumor nuclear size on staining with hematoxylin and eosin and omental texture on contrast-enhanced computed tomography, associated with prognosis. We found that these features contributed complementary prognostic information relative to one another and clinicogenomic features. By fusing histopathological, radiologic and clinicogenomic machine-learning models, we demonstrate a promising path toward improved risk stratification of patients with cancer through multimodal data integration.
| S-EPMC9239907 | biostudies-literature